SKILLEMALL.ai
GitHub ↗ RU Sign in

CB browser4-cli

Automates browser interactions for web testing, form filling, screenshots, and data extraction. Use when the user needs to navigate websites, interact with web pages, fill forms, take screenshots, test web applications, or extract information from web pages.

Not recommendedcritical or high security findings
ClawHub Agent Skills author: PlatonAI v0.1.0 MIT-0 36 files body ≈ 6 531 tokens Open the sourceclawhub.ai↗ analyzed 2 d ago

Automates browser interactions for web testing, form filling, screenshots, and data extraction.

As a process B 66/100 · Nearly there — weak spots: inputs and preconditions, failures and branches

IntegrationInfrastructuretype and topics are labelled automatically from the skill text
Runs in: OpenClaw Claude / Claude Code ChatGPT / Codex Gemini CLI Cursor GitHub Copilot / VS Code Qwen Code Kimi Code CLI Z.ai (GLM) DeepSeek (Deep Code) Mistral Vibe LangChain (deepagents) Goose OpenCode
JSON
Technical rating
C
74/100
safety, quality, tests
Safety 60%
72
Quality 40%
77
Run on models
none yet
Process rating
B
66/100
Nearly there
Inputs and preconditions w 11
0
Failures and branches w 10
0
Result and completion w 14
60
the three weakest of ten parameters · all ten

What is at stake

The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.

Exfiltration
If you install

The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".

For the author

If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.

How to improve

  1. Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
  2. The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
  • Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
  • A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.

Guard findings · 3

  • high Exfiltration intent-browser-credential-store SKILL.md:162
    Accesses a browser credential / cookie store
    | `profile-import` | Import bookmarks/history/passwords/cookies/extensions from system Chrome/Edge/Safari (requires the brow…ort plugin) | `profile-import --list-sources` to discover br
Medium and low: 2
  • medium Exfiltration intent-browser-credential-store references/browser-state-import.md:3
    Accesses a browser credential / cookie store (quoted — discussed, not commanded)
    description: "Reuse logged-in state (cookies, localStorage) or an entire profile from your system Chrome/Edge inside Brow…ged sessions. Covers attach + state-save/state-load, the deprecated SY
    quoted
  • medium Exfiltration intent-browser-credential-store references/browser-state-import.md:32
    Accesses a browser credential / cookie store (security demo / example)
    Use this when you need **logged-in state** (cookies + localStorage) from your system Chrome/Edge inside a Brow…ged session — e.g. to access authenticated pages without logging in again. Prefer
    demo

Files scanned: 36. Evidence is masked. Grey chips explain why severity was lowered.

Against the Agent Skills spec

  • warning body-long SKILL.md body ≈ 6531 tokens (recommended < 5000); move details to references/
  • note frontmatter-key unknown frontmatter key "title"
  • note frontmatter-key unknown frontmatter key "tier"

Process rating: all ten parameters 66/100

  • 0Inputs and preconditions. Does not say what the process needs to start
  • 0Failures and branches. Linear process with no failure handling
  • 60Result and completion. Output format stated, no completion criterion
  • 70When it triggers. States when to use, but not when not to
  • 70Execution cost. Instruction body is 6531 tokens
  • 85Steps. 22 steps, 2 vague phrases
  • 100Tools and files. Tools declared in frontmatter
  • 100Consistency. Name and required fields are in place
  • 100Running it twice. Mutating operations check current state
  • 100Progress reporting. Reports progress
  • medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
  • low The response is described with custom markup (12 tags): a typed call is more reliable

Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.

Quality signals

  • +5Description has no quoted example phrases that should trigger the skill
  • +4Description does not say when NOT to use the skill (false activations)
  • -2localhost URLs: will not work for another user
  • +1No license
  • +2Single-language instructions
  • +3Description length 258: enough signal without eating the budget
  • +4Structure: 19 headings
  • +3Step-by-step instructions: 22 items
  • +3Output format is stated explicitly
  • +4Has examples (9 code blocks)
  • +4Reference files are cited in the instructions (33 of 33)

Quality base 70; lint remarks subtract, signals add up to 100. Result: 77.

External checks

ClawHub: suspicious
This skill is mostly documented browser automation, but it also grants broad access to live browser sessions, saved login state, background execution, and skill-management actions that users should review carefully.
LLM: suspicious (high) · 1 Sept 2026